Automated Adenoid Hypertrophy Assessment with Lateral Cephalometry in Children Based on Artificial Intelligence

Abstract

Adenoid hypertrophy may lead to pediatric obstructive sleep apnea and mouth breathing. The routine screening of adenoid hypertrophy in dental practice is helpful for preventing relevant craniofacial and systemic consequences. The purpose of this study was to develop an automated assessment tool for adenoid hypertrophy based on artificial intelligence. A clinical dataset containing 581 lateral cephalograms was used to train the convolutional neural network (CNN). According to Fujioka’s method for adenoid hypertrophy assessment, the regions of interest were defined with four keypoint landmarks. The adenoid ratio based on the four landmarks was used for adenoid hypertrophy assessment. Another dataset consisting of 160 patients’ lateral cephalograms were used for evaluating the performance of the network. Diagnostic performance was evaluated with statistical analysis. The developed system exhibited high sensitivity (0.906, 95% confidence interval [CI]: 0.750–0.980), specificity (0.938, 95% CI: 0.881–0.973) and accuracy (0.919, 95% CI: 0.877–0.961) for adenoid hypertrophy assessment. The area under the receiver operating characteristic curve was 0.987 (95% CI: 0.974–1.000). These results indicated the proposed assessment system is able to assess AH accurately. The CNN-incorporated system showed high accuracy and stability in the detection of adenoid hypertrophy from children’ lateral cephalograms, implying the feasibility of automated adenoid hypertrophy screening utilizing a deep neural network model.

Application of Artificial Intelligence in Orthodontics: Current State and Future Perspectives

“…Screening the presence of upper-airway obstruction, especially adenoid hypertrophy, is critical for orthodontic diagnosis and treatment planning. The application of AI in upper-airway obstruction assessment is summarized in Table 3 [109][110][111][112][113][114][115][116][117]. Detecting adenoid hypertrophy based on lateral cephalograms has been proven to be highly accurate and reliable [118,119].…”

“…The adenoid-nasopharyngeal (AN) ratio proposed by Fujioka is the most notable method [120]. Both Shen et al and Zhao et al employed a CNN model to locate four key points in Fujioka's method on lateral cephalograms, and subsequently calculated the AN ratio [109,110]. The proposed model by Shen et al obtained a classification of 95.6% and a mean AN ratio error of 0.026 [68].…”

Inteligencia artificial en diagnóstico, pronóstico y planificación del tratamiento de alteraciones de la región cráneo-cérvico maxilofacial en ortodoncia. Revisión de la literatura

“…Para la evaluación de AH, en niños se o realiza por medio de una radiografía cefálica lateral, esta patología puede provocar apnea obstructiva del sueño o respiración oral. Mediante un CNN "HeadNet" se pretende evaluar esta patología basada en el método de "Fujioka", mostrando una alta sensibilidad (0.906, 95% CI: 0.750-0.980), especificidad (0.938, 95% CI: 0.881-0.973) y exactitud (0.919, 95% CI: 0.877-0.961), por lo que se podría usar para el diagnóstico de AH en niños (23).…”

Role of Laryngopharyngeal Reflux Changes in Children with Adenoid Hypertrophy: A Randomized Controlled Prospective Study

“…Adenoids are the immune organs of the body, containing lymphocytes at different stages of development [ 3 ]. Adenoid hypertrophy may block the eustachian tube's posterior nostril and pharyngeal orifice, leading to diseases of the adjacent organs [ 4 ]. One of the most critical complications of AH is obstructive sleep apnea (OSA), which has a significant impact on children's growth and learning [ 5 ].…”